Tavily Search

Real-time web search using Tavily API - search the web, extract page content, and get up-to-date information for RAG and research tasks

chainlesschain 4277fa2 2 files · 12.8 KB Updated

File contents

Tavily Search Skill

Real-time web search and content extraction using the Tavily API.

Usage

/tavily-search <query>
/tavily-search extract <url>

Modes

Mode Description Best For
search (default) Keyword-based web search Initial research, finding sources
extract Deep content extraction from URL Detailed analysis, specific pages

Setup

Set the TAVILY_API_KEY environment variable:

export TAVILY_API_KEY=tvly-your-api-key-here

Integration Pattern

  1. Use search for the discovery phase
  2. Analyze results to find relevant URLs
  3. Use extract for detailed content on specific URLs
  4. Process extracted content for user needs

Options

Option Values Description
search_depth basic, advanced Search depth (advanced costs more)
max_results 1-20 Maximum results to return
include_answer boolean Include AI-generated answer summary

Cost Considerations

  • Search is cheaper than extract
  • Use search to filter relevant URLs first
  • Only extract URLs that are likely relevant
  • basic depth is sufficient for most queries

chainlesschain/chainlesschain/tree/main/desktop-app-vue/src/main/ai-engine/cowork/skills/builtin/tavily-search commit 4277fa2aed

Frequently asked questions

npx skillmds@latest add chainlesschain/tavily-search